Business Analytics

Presenting Data Visualizations Effectively

Ayush Patel and Jayati sharma

25 March, 2024

Pre-requisite

You already…

Know data wrangling in R
Know data visualization in R
Understand different types of objects in R

Before we begin

Please install and load the following packages

library(tidyverse)
library(readxl)

Access lecture slide from the course landing page

About Me

I am Ayush.

I am a researcher working at the intersection of data, law, development and economics.

I teach Data Science using R at Gokhale Institute of Politics and Economics

I am a RStudio (Posit) certified tidyverse Instructor.

I am a Researcher at Oxford Poverty and Human development Initiative (OPHI), at the University of Oxford.

Reach me

ayush.ap58@gmail.com

ayush.patel@gipe.ac.in

Why is good visualization so important?

Every visualization has a story to tell, which requires skill
It is important that the reader presents data effectively, to prompt correct action or discussion
Data visualization is not a tool, it is a means for communicating results
To understand good visualization, let us take a look at

Say no to 3D graphs!

3D graphs makes the visualizations redundant and complex for no reason
The bars at the front hide the ones at the back.
Other than looking flashy, they almost never serve the purpose of conveying information
The tilt makes it even more difficult to read the values

The more, the merrier?

This graphic tries to show MLA salaries
The information overload makes it look aesthetically unpleasant
With all the information, it looks difficult to understand
Provided with such a visual, the audience would not be able to understand anything of substance

Misleading Visualization

Massive growth in iPhone sales, isn’t it?
However, a closer look shows that the sales are cumulative over time
Cumulative sales don’t necessarily show growth
Moreover, the graph does not have a scale on the y-axis
It isn’t clear what the graph is trying to show

Avoid Pie Charts

Pie chart, in most cases, are not the best approach to visualize data.
Not only do they add up to 100% in this case, they also make it difficult to comprehend which component has the biggest share
When you choose a donut chart, you are essentially asking your audience to measure the arc length to see which has the biggest share
Redundant, no? A simple bar chart would have done the job

Always a zero baseline

There seems to be a major difference between democrats and republicans for percent of people who agreed with court
However, at a closer look, the visualization has been made with a baseline of 50% which means that the difference is only around 8%
Graphs must always be made with a zero baseline to not exaggerate the scale

Making a good graph

Content for this topic has been sourced from Cole Nussbaumer Knaflic’s Storytelling with Data: A Data Visualization Guide for Business Professionals’. Please check out his work for detailed information.

Understand the context

Your visualization should not just present data
It should ask for an action and convey a point
For this, you need to know exactly what piece of information you want to convey
Your visualizations becomes a means for this communication

Making a good graph

Content for this topic has been sourced from Cole Nussbaumer Knaflic’s Storytelling with Data: A Data Visualization Guide for Business Professionals’. Please check out his work for detailed information.

Choosing the right visual

Text isn’t always bad!
Line graph for trends over time
Bar graph for categories
Scatterplot - relationship between two variables
Pie charts - what do you think?

Making a good graph

Content for this topic has been sourced from Cole Nussbaumer Knaflic’s Storytelling with Data: A Data Visualization Guide for Business Professionals’. Please check out his work for detailed information.

Avoid clutter

Understand and reduce load while making visualizations
Only focus on what you want to convey

Making a good graph

Content for this topic has been sourced from Cole Nussbaumer Knaflic’s Storytelling with Data: A Data Visualization Guide for Business Professionals’. Please check out his work for detailed information.

Focus your audience’s attention

Need for visual cues
Colour is an important tool for that

Before

After

Let’s replicate some graphs!

Download the data
Run the code with your own file path to import the data in R

rbi_ccs_data <- read_xlsx(
                          "/Users/jayatisharma/Documents/GitHub/GIPE-Business-Analytics/Consumer Confidence Survey _ Unit Level Data.xlsx"
                          )

Let’s replicate some graphs!

Try replicating this graph with the data

Source : Twitter

rbi_ccs_data <- rbi_ccs_data |>
  select(`Average Monthly Income`, `Perception on General Economic condition - compared to one year ago`) |>
  filter(`Perception on General Economic condition - compared to one year ago` != "Remained The Same")

rbi_ccs_percent <- rbi_ccs_data %>%
  group_by(`Average Monthly Income`, `Perception on General Economic condition - compared to one year ago`) %>%
  summarise(Count = n()) %>%
  mutate(Total = sum(Count), Percentage = Count / Total * 100)

ggplot(rbi_ccs_percent, aes(x = `Average Monthly Income`, y = Percentage, fill = `Perception on General Economic condition - compared to one year ago`)) +
  geom_bar(stat = "identity", position = "dodge") +
  theme_minimal() +
  labs(x = "Income Group", y = "Percentage", fill = "Perception") +
  scale_fill_brewer(palette = "Pastel1") +# This changes the color scheme, optional
  coord_flip()